Triple

T4248932
Position Surface form Disambiguated ID Type / Status
Subject Sulayman Chappelle E95796 entity
Predicate hasSibling P363 FINISHED
Object Sanaa Chappelle E90929 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sanaa Chappelle | Statement: [Sulayman Chappelle, hasSibling, Sanaa Chappelle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanaa Chappelle
Context triple: [Sulayman Chappelle, hasSibling, Sanaa Chappelle]
  • A. Sanaa Chappelle chosen
    Sanaa Chappelle is an American child actress best known for appearing alongside her father, comedian Dave Chappelle, in the film "A Star Is Born" (2018).
  • B. Issa Rae
    Issa Rae is an American actress, writer, and producer best known for creating and starring in the HBO series "Insecure."
  • C. Tiffany Haddish
    Tiffany Haddish is an American stand-up comedian and actress known for her breakout role in "Girls Trip" and her energetic, unfiltered comedic style.
  • D. Lizz Winstead
    Lizz Winstead is an American comedian, writer, and political satirist best known as a co-creator and former head writer of the television news parody program The Daily Show.
  • E. Wanda Sykes
    Wanda Sykes is an American stand-up comedian, actress, and writer known for her sharp, outspoken humor and roles in television, film, and voice acting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69b3453f759881909b91f01a1e82c036 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e9df10881908a2f039773f8afaa completed March 12, 2026, 11:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a87fdca481908bd2c80b10d0dd3d completed March 14, 2026, 6:27 p.m.
Created at: March 12, 2026, 11:06 p.m.